agentmods.dev

security-review

security-review is a command for Claude Code from Kenmege/codex-claude-companion. It costs 14 tokens per session (422 once invoked), scanned A, original, Apache-2.0.

A command that asks Claude to inspect the current Git workspace specifically for security problems. Git is a tool for tracking code changes, and a workspace is the project files being reviewed.

In plain words
What is it for?
Use it to review code for security risks, classify findings by common security categories, estimate how they could be exploited, and verify dependency vulnerability claims against lockfiles.
Why use it?
It helps find vulnerabilities that a general code review may miss, such as broken access checks, injection attacks, leaked secrets, unsafe file access, and known dependency flaws.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions Claude Code; mentions Codex.

not rated 2repo 6d ago A scan 14 tokens original Apache-2.0

Good fit Use it to review code for security risks, classify findings by common security categories, estimate how they could be exploited, and verify dependency vulnerability claims against lockfiles.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kenmege/codex-claude-companion/security-review
View source ↗ Kenmege/codex-claude-companion
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Kenmege/codex-claude-companion

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/security-review/github.svg)](https://agentmods.dev/commands/kenmege/codex-claude-companion/security-review)
Your own site
<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/security-review"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/security-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/security-review"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00422
Opus 5 $0.00007 $0.00211
Sonnet 5 $0.00003 $0.00084
Haiku 4.5 $0.00001 $0.00042

Measured 9d ago against content hash 987033279690, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/security-review.md · 58 lines

What it actually says

/claude-review:security-review

Preflight

  1. Prefer the helper binary codex-claude if it is available on PATH.
  2. If it is not available, tell the user to install the helper with npm install -g codex-claude-companion after npmjs publish, or from a cloned checkout with npm install -g ..

Plan

Runs an agentic Claude pass focused entirely on security risks: authz/authn bypass, injection (SQL/XSS/command/template/SSTI), SSRF, deserialization, path traversal, secret leakage, weak crypto, TLS misuse, race conditions in security checks, privilege escalation, and dependency CVEs.

Findings are mapped to OWASP/CWE in risk_category and classified by exploitability (pre-auth-remote, post-auth-remote, local, requires-misconfig). Dependency CVE claims are verified against the workspace lockfiles before being reported.

Default model is Claude Code's opus alias at xhigh effort.

Commands

Use the exact argument tail the user supplied after /claude-review:security-review.

  • Preferred: codex-claude security-review <user-arguments>

Useful flags:

  • --background for large diffs.
  • --mcp-config <file-or-json> to attach a CVE/security MCP.
  • --max-budget-usd <n> to cap spend.
  • --add-dir <path> to grant tool access to monorepo siblings or vendored source directories.

Keep this command read-only.

Verification

If the helper exits non-zero, report that failure exactly and stop.

Summary

Return the helper stdout verbatim.

Next Steps

For a broader code-quality pass, suggest /claude-review:elite-review or /claude-review:deep-review.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 58 lines · 14 tokens per session scan A 987033279690

Subscribe to this mod's changes

security-review is a command published in the GitHub repository Kenmege/codex-claude-companion (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 14 tokens to every session and 422 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeCode reviewSecurityagenticai-code-reviewclaudecodex
Related

Other commands, from other repositories

lint

Check the project for naming, security and best-practice issues.

mendixlabs/mxcli · 12 tokens

pi-code-review

Adversarial code review via Codex — break confidence in changes, not validate them.

tznthou/claude-prism · 17 tokens

pi-fact-check

Fact-check content via Gemini search + Claude verification — cross-provider claim validation.

tznthou/claude-prism · 14 tokens

pi-askall

Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.

tznthou/claude-prism · 16 tokens

pi-ask-gemini

Ask Gemini a question — get Google's perspective alongside Claude's.

tznthou/claude-prism · 11 tokens

conventions-check

Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.

eugenelim/agent-ready-repo · 28 tokens